Traceable TTS: Toward Watermark-Free TTS with Strong Traceability

arXiv:2507.03887 · eess.AS, cs.AI · Submitted 2025-07-05 · Read on arXiv

eess.AS, cs.AI

Submitted: 2025-07-05

Updated: 2025-07-05

Code: https://github.com/SWivid/F5-TTS

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 17× in this paper · explained in 13 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Robustness — 8× in this paper · explained in 5 episodes
• AUC — 6× in this paper · explained in 2 episodes
• Feature Extraction — 5× in this paper · explained in 2 episodes
• Loss Function — 5× in this paper · explained in 2 episodes
• Contrastive Learning — 4× in this paper · explained in 5 episodes
• Core — 4× in this paper · explained in 2 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Fingerprinting — 3× in this paper · explained in 2 episodes
• Self-Supervised Learning — 3× in this paper · explained in 8 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Generative Models — 2× in this paper · explained in 3 episodes
• Receiver Operating Characteristic — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Equal Error Rate — 1× in this paper
• False Positive Rate — 1× in this paper
• Generative Adversarial Network — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Lightweight Convolutional Neural Network — 1× in this paper
• Mean Opinion Scores — 1× in this paper
• Perplexity — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Word Error Rate — 1× in this paper

Sources

• WavMark: Watermarking for Audio Generation
• F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
• CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
• CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
• GLTR: Statistical Detection and Visualization of Generated Text
• RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification
• BigVGAN: A Universal Neural Vocoder with Large-Scale Training
• Origin Tracing and Detecting of LLMs
• Synthetic Speech Classification: IEEE Signal Processing Cup 2022 challenge
• P2Mark: Plug-and-play Parameter-level Watermarking for Neural Speech Generation
• UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
• Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling
• Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
• MUSAN: A Music, Speech, and Noise Corpus
• Few-Shot Detection of Machine-Generated Text using Style Representations
• A Survey on Neural Speech Synthesis
• Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
• Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
• LLMDet: A Third Party Large Language Models Generated Text Detection Tool
• DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

Related papers

• X-VC: Zero-shot Streaming Voice Conversion in Codec Space
• Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
• Towards Audio Token Compression in Large Audio Language Models
• WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection
• ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions